© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 4706
    Prev
    Next
    INDEX
    Explanations

    designed experiments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    æĭ¾
    -0.08
     اÙĦÙħÙĥت
    -0.07
    顺åĪ©éĢļè¿ĩ
    -0.07
    移è¡Į
    -0.07
     feminine
    -0.07
    该åIJį
    -0.07
    вÑĮÑİ
    -0.07
    åIJ«æľīçļĦ
    -0.07
    SSIP
    -0.07
    lect
    -0.07
    POSITIVE LOGITS
     experiments
    0.15
    å®ŀéªĮ
    0.14
     tests
    0.13
     experiment
    0.13
     testing
    0.13
    æµĭè¯ķ
    0.13
     test
    0.12
    experiment
    0.12
    çļĦå®ŀéªĮ
    0.11
     conducted
    0.11
    Activations Density 0.411%

    No Known Activations